]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rutube.py
Fix extraction from youtube.
[youtubedl] / youtube_dl / extractor / rutube.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5 import itertools
6
7 from .common import InfoExtractor
8 from ..compat import (
9 compat_str,
10 compat_parse_qs,
11 compat_urllib_parse_urlparse,
12 )
13 from ..utils import (
14 determine_ext,
15 bool_or_none,
16 int_or_none,
17 try_get,
18 unified_timestamp,
19 url_or_none,
20 )
21
22
23 class RutubeBaseIE(InfoExtractor):
24 def _extract_video(self, video, video_id=None, require_title=True):
25 title = video['title'] if require_title else video.get('title')
26
27 age_limit = video.get('is_adult')
28 if age_limit is not None:
29 age_limit = 18 if age_limit is True else 0
30
31 uploader_id = try_get(video, lambda x: x['author']['id'])
32 category = try_get(video, lambda x: x['category']['name'])
33
34 return {
35 'id': video.get('id') or video_id,
36 'title': title,
37 'description': video.get('description'),
38 'thumbnail': video.get('thumbnail_url'),
39 'duration': int_or_none(video.get('duration')),
40 'uploader': try_get(video, lambda x: x['author']['name']),
41 'uploader_id': compat_str(uploader_id) if uploader_id else None,
42 'timestamp': unified_timestamp(video.get('created_ts')),
43 'category': [category] if category else None,
44 'age_limit': age_limit,
45 'view_count': int_or_none(video.get('hits')),
46 'comment_count': int_or_none(video.get('comments_count')),
47 'is_live': bool_or_none(video.get('is_livestream')),
48 }
49
50
51 class RutubeIE(RutubeBaseIE):
52 IE_NAME = 'rutube'
53 IE_DESC = 'Rutube videos'
54 _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
55
56 _TESTS = [{
57 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
58 'md5': '79938ade01294ef7e27574890d0d3769',
59 'info_dict': {
60 'id': '3eac3b4561676c17df9132a9a1e62e3e',
61 'ext': 'flv',
62 'title': 'Раненный кенгуру забежал в аптеку',
63 'description': 'http://www.ntdtv.ru ',
64 'duration': 80,
65 'uploader': 'NTDRussian',
66 'uploader_id': '29790',
67 'timestamp': 1381943602,
68 'upload_date': '20131016',
69 'age_limit': 0,
70 },
71 }, {
72 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
73 'only_matching': True,
74 }, {
75 'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
76 'only_matching': True,
77 }, {
78 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
79 'only_matching': True,
80 }, {
81 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
82 'only_matching': True,
83 }]
84
85 @classmethod
86 def suitable(cls, url):
87 return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
88
89 @staticmethod
90 def _extract_urls(webpage):
91 return [mobj.group('url') for mobj in re.finditer(
92 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
93 webpage)]
94
95 def _real_extract(self, url):
96 video_id = self._match_id(url)
97
98 video = self._download_json(
99 'http://rutube.ru/api/video/%s/?format=json' % video_id,
100 video_id, 'Downloading video JSON')
101
102 info = self._extract_video(video, video_id)
103
104 options = self._download_json(
105 'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
106 video_id, 'Downloading options JSON',
107 headers=self.geo_verification_headers())
108
109 formats = []
110 for format_id, format_url in options['video_balancer'].items():
111 ext = determine_ext(format_url)
112 if ext == 'm3u8':
113 formats.extend(self._extract_m3u8_formats(
114 format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
115 elif ext == 'f4m':
116 formats.extend(self._extract_f4m_formats(
117 format_url, video_id, f4m_id=format_id, fatal=False))
118 else:
119 formats.append({
120 'url': format_url,
121 'format_id': format_id,
122 })
123 self._sort_formats(formats)
124
125 info['formats'] = formats
126 return info
127
128
129 class RutubeEmbedIE(InfoExtractor):
130 IE_NAME = 'rutube:embed'
131 IE_DESC = 'Rutube embedded videos'
132 _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
133
134 _TESTS = [{
135 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
136 'info_dict': {
137 'id': 'a10e53b86e8f349080f718582ce4c661',
138 'ext': 'flv',
139 'timestamp': 1387830582,
140 'upload_date': '20131223',
141 'uploader_id': '297833',
142 'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
143 'uploader': 'subziro89 ILya',
144 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
145 },
146 'params': {
147 'skip_download': True,
148 },
149 }, {
150 'url': 'http://rutube.ru/play/embed/8083783',
151 'only_matching': True,
152 }]
153
154 def _real_extract(self, url):
155 embed_id = self._match_id(url)
156 webpage = self._download_webpage(url, embed_id)
157
158 canonical_url = self._html_search_regex(
159 r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
160 'Canonical URL')
161 return self.url_result(canonical_url, RutubeIE.ie_key())
162
163
164 class RutubePlaylistBaseIE(RutubeBaseIE):
165 def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
166 return self._PAGE_TEMPLATE % (playlist_id, page_num)
167
168 def _entries(self, playlist_id, *args, **kwargs):
169 next_page_url = None
170 for pagenum in itertools.count(1):
171 page = self._download_json(
172 next_page_url or self._next_page_url(
173 pagenum, playlist_id, *args, **kwargs),
174 playlist_id, 'Downloading page %s' % pagenum)
175
176 results = page.get('results')
177 if not results or not isinstance(results, list):
178 break
179
180 for result in results:
181 video_url = url_or_none(result.get('video_url'))
182 if not video_url:
183 continue
184 entry = self._extract_video(result, require_title=False)
185 entry.update({
186 '_type': 'url',
187 'url': video_url,
188 'ie_key': RutubeIE.ie_key(),
189 })
190 yield entry
191
192 next_page_url = page.get('next')
193 if not next_page_url or not page.get('has_next'):
194 break
195
196 def _extract_playlist(self, playlist_id, *args, **kwargs):
197 return self.playlist_result(
198 self._entries(playlist_id, *args, **kwargs),
199 playlist_id, kwargs.get('playlist_name'))
200
201 def _real_extract(self, url):
202 return self._extract_playlist(self._match_id(url))
203
204
205 class RutubeChannelIE(RutubePlaylistBaseIE):
206 IE_NAME = 'rutube:channel'
207 IE_DESC = 'Rutube channels'
208 _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
209 _TESTS = [{
210 'url': 'http://rutube.ru/tags/video/1800/',
211 'info_dict': {
212 'id': '1800',
213 },
214 'playlist_mincount': 68,
215 }]
216
217 _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
218
219
220 class RutubeMovieIE(RutubePlaylistBaseIE):
221 IE_NAME = 'rutube:movie'
222 IE_DESC = 'Rutube movies'
223 _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
224 _TESTS = []
225
226 _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
227 _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
228
229 def _real_extract(self, url):
230 movie_id = self._match_id(url)
231 movie = self._download_json(
232 self._MOVIE_TEMPLATE % movie_id, movie_id,
233 'Downloading movie JSON')
234 return self._extract_playlist(
235 movie_id, playlist_name=movie.get('name'))
236
237
238 class RutubePersonIE(RutubePlaylistBaseIE):
239 IE_NAME = 'rutube:person'
240 IE_DESC = 'Rutube person videos'
241 _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
242 _TESTS = [{
243 'url': 'http://rutube.ru/video/person/313878/',
244 'info_dict': {
245 'id': '313878',
246 },
247 'playlist_mincount': 37,
248 }]
249
250 _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
251
252
253 class RutubePlaylistIE(RutubePlaylistBaseIE):
254 IE_NAME = 'rutube:playlist'
255 IE_DESC = 'Rutube playlists'
256 _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
257 _TESTS = [{
258 'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
259 'info_dict': {
260 'id': '3097',
261 },
262 'playlist_count': 27,
263 }, {
264 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
265 'only_matching': True,
266 }]
267
268 _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
269
270 @classmethod
271 def suitable(cls, url):
272 if not super(RutubePlaylistIE, cls).suitable(url):
273 return False
274 params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
275 return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
276
277 def _next_page_url(self, page_num, playlist_id, item_kind):
278 return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
279
280 def _real_extract(self, url):
281 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
282 playlist_kind = qs['pl_type'][0]
283 playlist_id = qs['pl_id'][0]
284 return self._extract_playlist(playlist_id, item_kind=playlist_kind)